Joined February 2025
- Tweets 46
- Following 7
- Followers 106
- Likes 27
21 Photos and videos
We are at @seattlefloworg sharing what we’re building at @AIPredictable.
We'll be at the Startup Fair. Live demos of @predictablecode, great conversations, and a lot more coming soon ❤️
May 15
Back at Bell Harbor, but this time with a very different perspective.
We’re here at @seattlefloworg representing @AIPredictable and sharing a live demo of @predictablecode ❤️
2
110
The one question I keep coming back to with AI-generated code: does it actually do what I specified?
Our first @PredictableCode case study answers that end-to-end on a real Java codebase, with a full recording of the workflow.
predictablemachines.com/blog…
1
2
3
891
For every deviation between code and spec, three options:
→ Fix the code (scoped prompt, can't break other contracts)
→ Update the spec (if your intent was different)
→ Remove the spec (if it no longer applies)
1
31
That's how Predictable Code keeps AI-generated code aligned with what you actually specified. No surprises, no quiet deviations.
Full case study with the complete recording here:
predictablemachines.com/blog…
28
We'll be at @seattlefloworg Startup Day 2026 on May 15th, demoing @PredictableCode at the Startup Fair.
Come see what it looks like to formally verify AI-generated code. Not "passes review," actually proven correct. 👌
Tickets 👉 seattleflow.org/startupday
3
2
159
Predictable Machines retweeted
May 7
The last article of the #AICodePainPoints series is done! (For now, because every improvement in this field brings new issues with it.)
This time, it's about what happens when a developer clicks Merge on AI-generated code reviewed by another AI. What are they actually approving? And in regulated industries, who carries the weight when something breaks?
The accountability didn't disappear. It just concentrated in one click.
AI writes the code.
AI reviews the code.
A developer clicks "merge" in under 10 minutes.
In that single click, all the legal and regulatory liability concentrates in one human, for code they didn't write and couldn't fully read.
2
3
782
AI writes the code.
AI reviews the code.
A developer clicks "merge" in under 10 minutes.
In that single click, all the legal and regulatory liability concentrates in one human, for code they didn't write and couldn't fully read.
1
1
3
447
The final piece of our #AICodePainPoints series is up: the merge button and the weight it carries.
predictablemachines.com/blog…
1
2
189
Predictable Machines retweeted
May 6
Uno de los amigos que ayer hizo demo fue @Jorge__Galindo con su @AIPredictable .
Está escribiendo unos blogposts majos sobre cómo su bicho ayuda a solventar los pain points habituales de programar con IA, pero en su caso con clientes corporate para cosas serias (no el vibecodeo de pachanga que flexeamos por aquí).
Echadle un ojo, que merece la pena aprender sobre el curro que tiene el garantizar que tienes unas specs capaces de superar auditorías corporate, y no un markdown slopeado de esos...
predictablemachines.com/blog…
May 5
no me puedo juntar con mis panas... tras el anuncio del ficha estrella, he visto 3 demos de productos que están lanzando/haciendo con IA... y yo ahora a enviar IRLs para comerme varias duedils antes de verano 😭
joder qué descolgado me estoy quedando de la vida...
1
6
14
2,695
Predictable Machines retweeted
May 6
If you are curious about knowing the different pain points we see in the ai generated code, and how we think we can help, this series of articles could be interesting to you 😊
Every team has a doc that's quietly become a lie.
The README wasn't updated when the API changed. The Notion page from six months ago.
We used to shrug at it. Then we started pasting it into Claude as context for the next feature.
1
2
321
Every team has a doc that's quietly become a lie.
The README wasn't updated when the API changed. The Notion page from six months ago.
We used to shrug at it. Then we started pasting it into Claude as context for the next feature.
1
2
2
592
Documentation stopped being just for the team. It's now the context for every line of code your AI is about to write.
Third piece of our pain points series: predictablemachines.com/blog…
54
Code that runs, compiles, passes tests, and still isn't doing what you asked.
Same requirement, three AI sessions, three incompatible implementations.
The second piece of our pain points series is up.
predictablemachines.com/blog…
2
5
354
Predictable Machines retweeted
Apr 21
Software engineers, PMs, designers, and CS / ML / MBA students: We're doing a Startup Fair @ Startup Day 2026.
Builders from @getclarify @yoodli @ItsClearlyAI @AIPredictable and more will talk product, tech, and their roles. No recruiters.
May 15. Free.
3
6
321
Ten developers, ten AI sessions, ten slightly different ideas of what the codebase is supposed to do.
First of a short series on the pain points we're solving with Predictable Code.
predictablemachines.com/blog…
1
3
674
Predictable Machines retweeted
Mar 24
Boring code meets exciting new tech 😮
We just open-sourced lean4-json-schema: derive JSON Schema from Lean 4 types, with a compile-time proof that serialization always validates against it.
No more trusting. The compiler checks it. 🧵
predictablemachines.com/blog…
1
7
688
We just open-sourced lean4-json-schema: derive JSON Schema from Lean 4 types, with a compile-time proof that serialization always validates against it.
No more trusting. The compiler checks it. 🧵
predictablemachines.com/blog…
1
3
1,286
Most JSON Schema bugs are silent. Your type says one thing, your serializer does another, your schema says a third. You find out at runtime.
lean4-json-schema makes those three things the same thing, by construction. If they don't agree, your code doesn't compile.
1
1
67
Second open source library we're publishing as we build @PredictableMachines. The first was lean4-markdown. More coming.
We need them ourselves. Figured others might too.
#Lean4 #OpenSource #FormalVerification @leanprover
2
55